Related papers: Exploring Data Pipelines through the Process Lens:…

Concept Bottleneck Models (CBMs) improve the explainability of black-box Deep Learning (DL) by introducing intermediate semantic concepts. However, standard CBMs often overlook domain-specific relationships and causal mechanisms, and their…

Large Vision-Language Models (LVLMs) have experienced significant advancements in recent years. However, their performance still falls short in tasks requiring deep visual perception, such as identifying subtle differences between images. A…

In the last few years we have seen a growing interest in machine learning approaches to computer vision and, especially, to semantic labeling. Nowadays state of the art systems use deep learning on millions of labeled images with very…

Document parsing (DP) transforms unstructured or semi-structured documents into structured, machine-readable representations, enabling downstream applications such as knowledge base construction and retrieval-augmented generation (RAG).…

Modern vision-based reinforcement learning techniques often use convolutional neural networks (CNN) as universal function approximators to choose which action to take for a given visual input. Until recently, CNNs have been treated like…

The reliable prediction of the temporal behavior of complex systems is key in numerous scientific fields. This strong interest is however hindered by modeling issues: often, the governing equations describing the physics of the system under…

Transfer learning has become an essential tool in modern computer vision, allowing practitioners to leverage backbones, pretrained on large datasets, to train successful models from limited annotated data. Choosing the right backbone is…

Current vision systems are trained on huge datasets, and these datasets come with costs: curation is expensive, they inherit human biases, and there are concerns over privacy and usage rights. To counter these costs, interest has surged in…

Meta-learning, or learning to learn, is a machine learning approach that utilizes prior learning experiences to expedite the learning process on unseen tasks. As a data-driven approach, meta-learning requires meta-features that represent…

An increasingly important aspect of designing recommender systems involves considering how recommendations will influence consumer choices. This paper addresses this issue by introducing a method for collecting user beliefs about…

A core component of human intelligence is the ability to identify abstract patterns inherent in complex, high-dimensional perceptual data, as exemplified by visual reasoning tasks such as Raven's Progressive Matrices (RPM). Motivated by the…

The construction of business process models has become an important requisite in the analysis and optimization of processes. The success of the analysis and optimization efforts heavily depends on the quality of the models. Therefore, a…

In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream…

A rapidly growing number of voices argue that AI research, and computer vision in particular, is powering mass surveillance. Yet the direct path from computer vision research to surveillance has remained obscured and difficult to assess.…

Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the…

Increasingly larger number of software systems today are including data science components for descriptive, predictive, and prescriptive analytics. The collection of data science stages from acquisition, to cleaning/curation, to modeling,…

The recently increased complexity of Machine Learning (ML) methods, led to the necessity to lighten both the research and industry development processes. ML pipelines have become an essential tool for experts of many domains, data…

Process mining involves discovering, monitoring, and improving real processes by extracting knowledge from event logs in information systems. Process mining has become an important topic in recent years, as evidenced by a growing number of…

Process mining enables the reconstruction and evaluation of business processes based on digital traces in IT systems. An increasingly important technique in this context is process prediction. Given a sequence of events of an ongoing trace,…

We investigate two crucial and closely related aspects of CNNs for optical flow estimation: models and training. First, we design a compact but effective CNN model, called PWC-Net, according to simple and well-established principles:…